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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a direction or destination

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.78
    ressor
    -0.66
    ãĥ¤
    -0.65
    sylvania
    -0.64
     Rossi
    -0.63
    Tam
    -0.62
    opard
    -0.61
    iability
    -0.61
    hma
    -0.59
    ania
    -0.58
    POSITIVE LOGITS
    canon
    0.96
    heading
    0.92
     toward
    0.84
     towards
    0.83
    stones
    0.82
    lander
    0.82
    line
    0.77
    quarter
    0.75
    butt
    0.74
    ////////////////////////////////
    0.73
    Act Density 0.011%

    No Known Activations