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

    Neuronpedia

    INDEX
    Explanations

    locations and personal details

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases related to specific statistical or demographic information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     applause
    -0.79
     reversible
    -0.68
     clutch
    -0.68
     omission
    -0.68
     consolation
    -0.68
     tremend
    -0.67
    tro
    -0.66
    raq
    -0.64
     equival
    -0.63
     captcha
    -0.63
    POSITIVE LOGITS
     Therefore
    1.16
     Its
    1.13
     Neither
    1.02
     They
    1.00
     Their
    0.98
     Currently
    0.98
     Located
    0.96
     Hence
    0.94
     Presumably
    0.94
     Consequently
    0.92
    Act Density 0.581%

    No Known Activations