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

    Neuronpedia

    INDEX
    Explanations

    indications of a call to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or recommendations to be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    person
    -0.77
    Sold
    -0.76
    hent
    -0.70
    raped
    -0.68
    listed
    -0.67
    rn
    -0.64
    DERR
    -0.59
     Beats
    -0.59
    backed
    -0.58
    volent
    -0.58
    POSITIVE LOGITS
     celebrate
    1.16
     revisit
    1.15
     settle
    1.06
     conserve
    1.02
     refresh
    0.99
     revise
    0.98
     retire
    0.96
     resolve
    0.92
     consolidate
    0.92
     introduce
    0.92
    Act Density 0.071%

    No Known Activations