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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.82
    ########.
    -0.67
     jScrollPane
    -0.65
     թվական
    -0.55
     sombr
    -0.53
     CreateTagHelper
    -0.52
    styr
    -0.52
    nativeElement
    -0.50
     chio
    -0.50
    WriteBarrier
    -0.49
    POSITIVE LOGITS
    EndContext
    0.54
     Ivor
    0.53
    tamol
    0.52
    啧
    0.52
    ślę
    0.51
    esez
    0.51
     Infórmanos
    0.50
    ovia
    0.50
    twimg
    0.50
    EqualsAnd
    0.49
    Act Density 0.001%

    No Known Activations