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

    Neuronpedia

    INDEX
    Explanations

    words related to phishing or misleading activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to phobia or fear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.87
    HCR
    -0.85
    CLASSIFIED
    -0.71
    TRY
    -0.68
     Paw
    -0.65
     Horror
    -0.64
     Arabia
    -0.64
     Pitch
    -0.64
    PRES
    -0.64
     Hussein
    -0.64
    POSITIVE LOGITS
    oenix
    1.46
    ilipp
    1.18
    allic
    1.17
    araoh
    1.12
    oning
    1.12
    antom
    1.11
    ysics
    1.10
    obia
    1.09
    agons
    1.08
    oned
    1.03
    Act Density 0.030%

    No Known Activations