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

    Neuronpedia

    INDEX
    Explanations

    references to actions, objects, or conditions that imply a state of being or processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateria
    -0.16
    witch
    -0.15
    undy
    -0.15
    775
    -0.15
    774
    -0.15
    544
    -0.15
    _ATTRIB
    -0.15
    869
    -0.15
    agy
    -0.14
    776
    -0.14
    POSITIVE LOGITS
    venta
    0.17
     Hu
    0.16
    pf
    0.15
    Hu
    0.14
    .Timeout
    0.14
    oren
    0.14
    orp
    0.13
    cntl
    0.13
    Ïģκ
    0.13
     Hull
    0.13
    Act Density 0.009%

    No Known Activations