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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to denial or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
    IContainer
    -0.54
    tvguidetime
    -0.54
    bacher
    -0.53
     aux
    -0.51
    postValue
    -0.51
    werfen
    -0.51
    DebuggerNonUser
    -0.51
    Сылтамалар
    -0.50
    polated
    -0.48
    POSITIVE LOGITS
     handleMessage
    0.87
    )";
    0.77
    __':
    0.71
    '>
    0.69
     BoxDecoration
    0.69
    ^(@)
    0.67
    ]`
    0.65
    ysław
    0.65
    >';
    0.64
    ;">
    0.62
    Act Density 0.210%

    No Known Activations