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

    Neuronpedia

    INDEX
    Explanations

    numerical data and transitions between numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.66
    #+#
    -0.63
    хьтан
    -0.62
     étoit
    -0.60
    WithMany
    -0.58
     pleaſure
    -0.56
    LookAnd
    -0.56
     itſelf
    -0.55
    StructEnd
    -0.54
     raiſ
    -0.54
    POSITIVE LOGITS
     again
    0.64
    again
    0.54
     Again
    0.51
     опять
    0.48
     AGAIN
    0.48
    Again
    0.47
     novamente
    0.43
     opět
    0.43
    AGAIN
    0.42
    又一次
    0.41
    Act Density 0.111%

    No Known Activations