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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the exclusion or dismissal of certain possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the denial or dismissal of possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.77
     conflic
    -0.75
    inki
    -0.73
    itialized
    -0.72
    elf
    -0.72
    iosyn
    -0.71
    awar
    -0.70
    omsky
    -0.69
     resil
    -0.69
    feel
    -0.67
    POSITIVE LOGITS
    posts
    0.83
    enance
    0.71
    nels
    0.69
     anything
    0.68
     pedestrians
    0.67
    stadt
    0.64
     negatives
    0.64
     dissenting
    0.63
     Sussex
    0.63
     Ernst
    0.62
    Act Density 0.031%

    No Known Activations