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

    Neuronpedia

    INDEX
    Explanations

    dialogue and speech-related actions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     сказали
    -0.47
    -0.45
    说过
    -0.44
    zzleHttp
    -0.42
    的问道
    -0.41
     قول
    -0.41
    saying
    -0.41
    说是
    -0.40
    说了
    -0.40
     thanked
    -0.40
    POSITIVE LOGITS
     sounding
    0.63
     Administrativna
    0.59
     referring
    0.59
     pointing
    0.59
     يتيمه
    0.59
     looking
    0.57
     <<<<<<<<<<<<<<
    0.56
     autorytatywna
    0.54
     rubbing
    0.53
     turning
    0.50
    Act Density 0.103%

    No Known Activations