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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    references to young individuals or children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %"
    -0.77
    Primary
    -0.68
    Firstly
    -0.64
     FILE
    -0.64
    },{"
    -0.64
    FILE
    -0.60
     Obj
    -0.59
    female
    -0.59
     NAME
    -0.59
     Username
    -0.59
    POSITIVE LOGITS
     extraord
    0.77
     lurking
    0.68
     likewise
    0.67
     poised
    0.67
     sprinkled
    0.66
    arthy
    0.65
     clutching
    0.65
     wondering
    0.64
     swallowing
    0.64
     headlined
    0.63
    Act Density 0.711%

    No Known Activations