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

    Neuronpedia

    INDEX
    Explanations

    instances of suspicion or uncertainty in contexts involving crime or abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ạ
    -0.15
    amento
    -0.14
    UTOR
    -0.14
    solete
    -0.13
    zew
    -0.13
    angu
    -0.13
    amentos
    -0.13
     sill
    -0.13
     Offline
    -0.13
    ocaly
    -0.13
    POSITIVE LOGITS
     suspect
    0.94
     Sus
    0.88
     suspects
    0.85
    sus
    0.84
     sus
    0.82
     suspicion
    0.82
    Sus
    0.81
     Susp
    0.80
     suspicious
    0.78
    Susp
    0.78
    Act Density 0.254%

    No Known Activations