Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or terms that are quoted, referred to, or identified as specific labels

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve referencing or labeling something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.70
    oration
    -0.69
    ooter
    -0.67
     earthqu
    -0.63
    artifacts
    -0.62
    yrus
    -0.60
    oppy
    -0.59
     teasp
    -0.58
    ————————————————
    -0.58
    lication
    -0.57
    POSITIVE LOGITS
    XM
    0.75
    illet
    0.72
    urally
    0.71
     termed
    0.69
    guards
    0.67
    called
    0.65
     eq
    0.65
    fit
    0.62
    /+
    0.62
     sizeof
    0.60
    Act Density 0.091%

    No Known Activations