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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or decisions that one entity imposes on another entity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obligations and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.77
    Guest
    -0.71
     Died
    -0.68
     extraord
    -0.67
     Martial
    -0.66
     hating
    -0.65
     Illuminati
    -0.65
    izoph
    -0.65
     hilarious
    -0.64
     boredom
    -0.63
    POSITIVE LOGITS
     reimburse
    1.17
     refund
    1.11
     reimb
    1.06
     subcontract
    1.05
     compensate
    1.02
     disclose
    0.99
     repay
    0.98
     undertake
    0.95
     reinvest
    0.94
     distribute
    0.93
    Act Density 0.300%

    No Known Activations