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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality or nature of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey strong qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.82
    thood
    -0.75
    arser
    -0.72
    hner
    -0.71
    elines
    -0.70
    ADRA
    -0.68
    livion
    -0.66
    ichever
    -0.66
    mbudsman
    -0.64
    umbs
    -0.61
    POSITIVE LOGITS
     indeed
    1.68
     considering
    0.95
     stuff
    0.86
    blooded
    0.84
     (~
    0.82
     compared
    0.80
     thing
    0.77
     sounding
    0.77
     nowadays
    0.77
     actually
    0.76
    Act Density 0.300%

    No Known Activations