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

    Neuronpedia

    INDEX
    Explanations

    references to hijackers or hijackings

    oai_token-act-pair · gpt-3.5-turbo

    references to hijacking activities and the individuals involved in them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rite
    -0.84
    20439
    -0.76
    ç¥ŀ
    -0.74
     Angels
    -0.73
    ãģ®éŃĶ
    -0.69
     Blessed
    -0.66
     Piercing
    -0.65
    Recommend
    -0.64
     Patron
    -0.61
    Reviewer
    -0.60
    POSITIVE LOGITS
     hij
    1.29
     hijacked
    0.97
    intosh
    0.95
    ackers
    0.91
    inx
    0.88
    ulence
    0.82
    eering
    0.81
    acking
    0.81
    acker
    0.77
    ibl
    0.77
    Act Density 0.007%

    No Known Activations