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

    Neuronpedia

    INDEX
    Explanations

    verbs that describe significant changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    significant changes or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.77
    ¶ħ
    -0.74
    enes
    -0.71
    etheless
    -0.70
    ctors
    -0.67
     subp
    -0.66
    sembly
    -0.65
    esan
    -0.65
    eeper
    -0.64
    speech
    -0.64
    POSITIVE LOGITS
    natureconservancy
    0.69
    resp
    0.62
    wn
    0.61
     Suite
    0.60
    lust
    0.60
     Pag
    0.60
    frey
    0.59
    oms
    0.59
    702
    0.59
    lest
    0.59
    Act Density 0.000%

    No Known Activations