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

    Neuronpedia

    INDEX
    Explanations

    references to the publication "Detroit Free Press"

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization "Free Press"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTS
    -0.74
    iop
    -0.73
    ysis
    -0.73
     therap
    -0.70
    uality
    -0.70
     bitters
    -0.67
    ional
    -0.67
    warts
    -0.67
     dece
    -0.65
     envy
    -0.65
    POSITIVE LOGITS
    zing
    1.14
    bie
    0.98
    bies
    0.98
    zer
    0.96
    zes
    0.95
    zers
    0.94
    gans
    0.91
    edom
    0.86
    BSD
    0.83
    NAS
    0.83
    Act Density 0.028%

    No Known Activations