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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating variability or inconsistency in conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.90
    writerow
    -0.64
     createSlice
    -0.61
    closedir
    -0.61
    MessageTagHelper
    -0.56
     ORGANISM
    -0.55
    Abp
    -0.55
    стоин
    -0.51
    WriteLiteral
    -0.51
    gotoxy
    -0.50
    POSITIVE LOGITS
     vague
    1.07
     haphazard
    1.03
     vaguely
    1.02
     loosely
    0.93
     inconclusive
    0.87
    poor
    0.86
     mediocre
    0.85
     poorly
    0.84
     sporadic
    0.83
     flimsy
    0.83
    Act Density 0.552%

    No Known Activations