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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to gaining entry or obtaining information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "access" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.66
    balls
    -0.65
    warming
    -0.61
    break
    -0.60
     abst
    -0.59
    yes
    -0.58
    cas
    -0.58
    inning
    -0.58
    ignore
    -0.58
     stint
    -0.57
    POSITIVE LOGITS
    ibly
    1.10
    ibility
    0.98
    IBLE
    0.88
    ible
    0.85
    ãĥ¼ãĥĨãĤ£
    0.79
    ioned
    0.77
    ibles
    0.77
    folios
    0.77
    ADRA
    0.77
    éŃĶ
    0.73
    Act Density 0.040%

    No Known Activations