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

    Neuronpedia

    INDEX
    Explanations

    announcement of plans or decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of announcements or declarations by entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soph
    -0.66
     brav
    -0.64
     precept
    -0.63
     defeats
    -0.60
    bole
    -0.58
    ecd
    -0.58
     cynicism
    -0.57
    conom
    -0.57
     circumstance
    -0.56
    isms
    -0.56
    POSITIVE LOGITS
    ija
    0.72
    inates
    0.68
     "#
    0.68
    ALLY
    0.67
    asca
    0.66
    çĶ°
    0.66
    uminati
    0.63
     finally
    0.62
    NAS
    0.61
     reopen
    0.60
    Act Density 0.353%

    No Known Activations