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

    Neuronpedia

    INDEX
    Explanations

    elements of suspicion and danger in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ATH
    -0.15
    ecut
    -0.15
    asthan
    -0.14
     Pru
    -0.14
     Adj
    -0.14
    ilim
    -0.14
    eries
    -0.13
    lift
    -0.13
    stry
    -0.13
     Joined
    -0.13
    POSITIVE LOGITS
     gió
    0.15
    ocup
    0.14
    afia
    0.13
    _ESCAPE
    0.13
     à¤ļल
    0.13
    .nih
    0.13
    734
    0.13
    ppo
    0.13
    obj
    0.13
     Barry
    0.13
    Act Density 0.032%

    No Known Activations