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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making changes or influencing decisions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs associated with political or governmental actions and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortunately
    -0.68
    pmwiki
    -0.68
    Laughs
    -0.67
     whim
    -0.67
    claimer
    -0.65
    Sym
    -0.65
    ":"/
    -0.64
    ammy
    -0.63
    sis
    -0.61
    jac
    -0.61
    POSITIVE LOGITS
    igate
    0.75
    enance
    0.74
    uate
    0.66
    eport
    0.66
     contraceptives
    0.65
     MH
    0.64
     glyphosate
    0.63
     broadband
    0.62
     transgender
    0.62
     Hungary
    0.62
    Act Density 0.300%

    No Known Activations