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

    Neuronpedia

    INDEX
    Explanations

    negative statements or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anj
    -0.15
    I
    -0.14
     competitor
    -0.14
     Jimmy
    -0.14
    競
    -0.14
    754
    -0.14
    le
    -0.14
    oard
    -0.13
    331
    -0.13
     latter
    -0.13
    POSITIVE LOGITS
    /-
    0.19
    uggage
    0.15
     UIResponder
    0.15
    _PULL
    0.15
    .scalablytyped
    0.15
    untime
    0.14
    PIO
    0.14
    WSC
    0.14
    #__
    0.14
    /autoload
    0.14
    Act Density 0.016%

    No Known Activations