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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to taking action or making an effort

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.64
     wont
    -0.54
    quartered
    -0.50
    torn
    -0.48
    obs
    -0.48
    blogspot
    -0.48
    >>\
    -0.47
    itcher
    -0.47
    jar
    -0.46
    DragonMagazine
    -0.45
    POSITIVE LOGITS
     oneself
    0.95
    uate
    0.84
    enance
    0.82
    ulate
    0.77
    igate
    0.69
    itate
    0.66
    ISE
    0.65
     yourself
    0.64
     them
    0.64
    dress
    0.64
    Act Density 0.708%

    No Known Activations