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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and relational terms

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that are left in vulnerable or exposed situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haps
    -0.68
    wcsstore
    -0.63
     =>
    -0.61
    imum
    -0.60
    oho
    -0.60
    deals
    -0.59
     Encyclopedia
    -0.59
     confir
    -0.59
    idth
    -0.58
    afort
    -0.58
    POSITIVE LOGITS
     stranded
    1.24
     untouched
    1.24
     vulnerable
    1.16
     unprotected
    1.16
     powerless
    1.14
     alone
    1.12
     uninsured
    1.12
     unatt
    1.11
     dangling
    1.09
     intact
    1.09
    Act Density 0.091%

    No Known Activations