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

    Neuronpedia

    INDEX
    Explanations

    negation or denial phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WritableDatabase
    -0.72
    OGND
    -0.67
    seamnă
    -0.66
     gradova
    -0.65
     Meksiku
    -0.65
     gjø
    -0.64
     estekak
    -0.64
     AppColors
    -0.64
    batore
    -0.64
     Efq
    -0.63
    POSITIVE LOGITS
     Still
    0.56
    STILL
    0.55
    Still
    0.53
    "]();
    0.52
    devtools
    0.50
    etheless
    0.50
    יין
    0.49
    parsedMessage
    0.48
     restant
    0.48
    ]]
    0.47
    Act Density 0.120%

    No Known Activations