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

    Neuronpedia

    INDEX
    Explanations

    instances of interpersonal interactions and arrivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.15
    erken
    -0.14
    abcdefghijklmnop
    -0.14
    âī¡
    -0.14
     outing
    -0.14
    REEN
    -0.14
    YRO
    -0.13
    ADATA
    -0.13
    segue
    -0.13
     outings
    -0.13
    POSITIVE LOGITS
     arrive
    0.87
     Arr
    0.87
    arr
    0.85
     arrival
    0.82
     arrived
    0.82
    Arr
    0.82
     ARR
    0.79
     arrives
    0.79
     arr
    0.78
    _arr
    0.76
    Act Density 0.205%

    No Known Activations