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

    Neuronpedia

    INDEX
    Explanations

    verbs related to obtaining or achieving something

    oai_token-act-pair · gpt-3.5-turbo

    the word "secure" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.73
    balls
    -0.72
    mes
    -0.69
    mania
    -0.65
    timer
    -0.63
    laughter
    -0.63
    bow
    -0.63
    slow
    -0.63
    flat
    -0.61
    hops
    -0.61
    POSITIVE LOGITS
     assurances
    0.85
     passage
    0.78
     clearance
    0.76
     sufficient
    0.72
     stakes
    0.71
     fulfillment
    0.71
    cffff
    0.70
    RET
    0.70
     financing
    0.68
    kefeller
    0.67
    Act Density 0.021%

    No Known Activations