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

    Neuronpedia

    INDEX
    Explanations

    code-related terms that indicate data formatting and input handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.60
     Shreve
    -0.54
     Socialista
    -0.54
     springfox
    -0.51
     precipitates
    -0.50
    providedIn
    -0.50
     ElementRef
    -0.50
     classifica
    -0.49
    لسط
    -0.49
     conces
    -0.49
    POSITIVE LOGITS
     replace
    0.90
     replacements
    0.87
     replacement
    0.86
     Replace
    0.79
     replaced
    0.79
     Replacement
    0.78
    Replace
    0.76
     replacing
    0.76
     substitution
    0.76
    Replacement
    0.74
    Act Density 0.276%

    No Known Activations