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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating involvement and interaction in various experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spo
    -0.16
    onio
    -0.15
     Gesture
    -0.14
    maf
    -0.14
    arl
    -0.14
    iid
    -0.14
    gesture
    -0.14
    elez
    -0.14
    .Atomic
    -0.13
     coz
    -0.13
    POSITIVE LOGITS
     conversations
    0.22
     conversation
    0.21
     discussions
    0.20
     fun
    0.20
     difficulty
    0.19
     discussion
    0.18
     Difficulty
    0.18
     experiences
    0.18
     success
    0.17
    versations
    0.17
    Act Density 0.142%

    No Known Activations