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

    Neuronpedia

    INDEX
    Explanations

    action verbs and phrases that imply physical interaction or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.97
     suaminya
    -0.79
    they
    -0.76
     они
    -0.68
     we
    -0.67
    AutoScaleMode
    -0.61
    findpost
    -0.56
     marido
    -0.56
     svůj
    -0.54
    CloseOperation
    -0.53
    POSITIVE LOGITS
     henne
    1.07
     hende
    1.07
     us
    1.02
    OGND
    0.95
     OFDb
    0.92
     them
    0.88
     nela
    0.86
     ourselves
    0.84
     him
    0.81
     ją
    0.79
    Act Density 0.144%

    No Known Activations