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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a judgment or evaluation of a situation

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and related auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SPD
    -0.73
     Vers
    -0.66
     neutron
    -0.63
     fixation
    -0.62
     bond
    -0.62
     predicate
    -0.61
     Maced
    -0.61
     regress
    -0.59
     modernization
    -0.56
     eurozone
    -0.56
    POSITIVE LOGITS
    ©¶æ
    0.86
    hes
    0.86
    Ĥİ
    0.85
    chers
    0.83
    cher
    0.77
    si
    0.73
    rael
    0.73
    alde
    0.73
    abouts
    0.73
    hers
    0.71
    Act Density 0.896%

    No Known Activations