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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving sequences, transitions, or relationships between events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :[
    -0.83
    ortium
    -0.67
    ueller
    -0.66
    odore
    -0.56
     sho
    -0.55
     sacked
    -0.54
     Saban
    -0.54
     strugg
    -0.54
     forgiven
    -0.53
    urger
    -0.53
    POSITIVE LOGITS
     Kinnikuman
    0.79
    inks
    0.76
    tones
    0.75
     alike
    0.71
    URES
    0.70
    vals
    0.68
    wings
    0.67
    mes
    0.67
    ciation
    0.66
     guiActiveUnfocused
    0.66
    Act Density 0.942%

    No Known Activations