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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong commitment or promise

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vowed" indicating a promise or commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.73
     Ain
    -0.71
    EMS
    -0.70
    Occ
    -0.70
    nesota
    -0.67
    Kin
    -0.66
    geist
    -0.65
    psy
    -0.65
    umbn
    -0.65
    central
    -0.64
    POSITIVE LOGITS
     vows
    0.94
     vow
    0.94
     vowed
    0.82
     encour
    0.80
     anew
    0.78
    fulness
    0.70
     pledges
    0.70
     defiant
    0.70
    lessly
    0.69
     oath
    0.69
    Act Density 0.016%

    No Known Activations