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

    Neuronpedia

    INDEX
    Explanations

    words related to affirmation or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being affected by or suffering from a condition or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Crash
    -0.74
    rose
    -0.73
     Solitaire
    -0.71
    raz
    -0.69
     VC
    -0.68
    VC
    -0.68
    Gi
    -0.65
     =====
    -0.64
    runners
    -0.64
    planned
    -0.64
    POSITIVE LOGITS
     aff
    3.79
     Aff
    1.58
    Aff
    1.45
    aff
    1.22
     afflicted
    1.06
     affirm
    1.06
     cert
    1.05
     affinity
    1.02
     ail
    1.01
     asc
    1.01
    Act Density 0.012%

    No Known Activations