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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and certain prepositional phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendriers
    -0.59
    ″]
    -0.58
    arakhand
    -0.54
    baguna
    -0.54
    VIER
    -0.53
    InputModule
    -0.52
    LabelTagHelper
    -0.52
    BOA
    -0.52
     Infórmanos
    -0.50
    química
    -0.50
    POSITIVE LOGITS
     htons
    0.64
    ंदीखरीदारी
    0.56
     partea
    0.55
     consultato
    0.54
    Médaille
    0.54
    endaftaran
    0.52
    AutoScaleMode
    0.51
     fratello
    0.50
    gyz
    0.49
    BeginContext
    0.49
    Act Density 0.503%

    No Known Activations