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

    Neuronpedia

    INDEX
    Explanations

    actions related to assisting or helping others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.64
     occaf
    -0.61
     fevere
    -0.61
    Lähteet
    -0.58
     fubject
    -0.58
     doubtnut
    -0.56
     myſelf
    -0.56
     neceff
    -0.56
     ftate
    -0.55
     ſind
    -0.55
    POSITIVE LOGITS
    oneofs
    0.68
     greeted
    0.67
     subito
    0.63
    UnknownFieldSet
    0.63
    immediately
    0.60
     immediately
    0.60
     StatefulWidget
    0.58
    ########.
    0.57
     lateinit
    0.57
     into
    0.57
    Act Density 0.150%

    No Known Activations