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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transparence
    -0.53
     únicos
    -0.51
     wiele
    -0.49
    élève
    -0.48
     villaggio
    -0.48
     únicas
    -0.47
     vaisselle
    -0.46
     supérieures
    -0.46
    iega
    -0.46
    щет
    -0.45
    POSITIVE LOGITS
     grab
    1.25
     grabbing
    1.19
     Grab
    1.19
     grabbed
    1.18
    grab
    1.17
    Grab
    1.14
     grabs
    1.09
     slap
    0.91
     shove
    0.90
     slapped
    0.89
    Act Density 0.269%

    No Known Activations