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

    Neuronpedia

    INDEX
    Explanations

    verbs related to recognition or admission

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "acknowledge" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chn
    -0.75
    vic
    -0.73
    ixt
    -0.72
     handy
    -0.65
    nz
    -0.63
    hire
    -0.63
     inj
    -0.62
    aspx
    -0.61
     belts
    -0.60
    gm
    -0.59
    POSITIVE LOGITS
    ibly
    0.96
    ibility
    0.89
    enance
    0.88
    ably
    0.87
    ledged
    0.85
     acknowledging
    0.79
     acknowledges
    0.79
     acknowledge
    0.78
     acknowled
    0.77
    IBLE
    0.72
    Act Density 0.021%

    No Known Activations