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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing relationships of necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esez
    -0.57
    اریخ
    -0.55
     ajuns
    -0.53
    Personendaten
    -0.52
    cèse
    -0.52
     ***!
    -0.49
    ESOME
    -0.49
    Népesség
    -0.47
     resourceCulture
    -0.47
    acijos
    -0.47
    POSITIVE LOGITS
     nothing
    0.69
     anything
    0.61
     gemein
    0.61
    VersionUID
    0.61
     everything
    0.60
     تضيفلها
    0.59
    nothing
    0.59
    Nothing
    0.59
    Anything
    0.58
    everything
    0.57
    Act Density 0.217%

    No Known Activations