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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    30
    -0.17
     twenty
    -0.16
    ournée
    -0.15
     Twenty
    -0.14
    edis
    -0.14
    030
    -0.14
    éĺħ读次æķ°
    -0.14
    twenty
    -0.14
    .AutoScaleMode
    -0.14
    orthand
    -0.14
    POSITIVE LOGITS
    45
    0.25
    41
    0.23
    40
    0.23
    50
    0.23
    44
    0.23
    60
    0.23
    46
    0.23
    49
    0.22
    55
    0.22
    56
    0.22
    Act Density 0.050%

    No Known Activations