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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful actions or impactful changes

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs that imply a sense of impact or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.61
    journal
    -0.59
    usable
    -0.59
    lyss
    -0.58
     ·
    -0.57
     guiIcon
    -0.57
    ordan
    -0.56
    able
    -0.54
    AMY
    -0.53
    isable
    -0.53
    POSITIVE LOGITS
     forth
    0.80
     out
    0.77
     up
    0.73
     down
    0.69
     overboard
    0.68
     tongues
    0.67
     elbows
    0.66
     noses
    0.64
     away
    0.64
    atform
    0.64
    Act Density 0.371%

    No Known Activations