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

    Neuronpedia

    INDEX
    Explanations

    conditional or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.90
    ſelves
    -0.82
    ſelf
    -0.82
     itſelf
    -0.78
     ſche
    -0.77
     myſelf
    -0.76
     ―――――
    -0.73
     themſelves
    -0.73
     UPM
    -0.73
     poffible
    -0.71
    POSITIVE LOGITS
    thenReturn
    0.72
     Somit
    0.70
    +#+
    0.70
     then
    0.68
     مشين
    0.68
     it
    0.64
     саны
    0.63
     definitely
    0.61
    になれば
    0.60
     partenza
    0.59
    Act Density 0.065%

    No Known Activations