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

    Neuronpedia

    INDEX
    Explanations

    references to a specific person or entity in a position of authority

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.71
     erection
    -0.63
    INGTON
    -0.61
    undo
    -0.60
     Jr
    -0.60
    ENSE
    -0.59
     GEAR
    -0.59
    ustom
    -0.59
    VERTIS
    -0.59
     XIII
    -0.59
    POSITIVE LOGITS
    pher
    1.53
    athed
    1.40
    pard
    1.39
    pherd
    1.38
    ffield
    1.37
    athing
    1.34
    ldon
    1.30
    ikh
    1.20
    lled
    1.19
    bang
    1.16
    Act Density 0.079%

    No Known Activations