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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cooking and preparation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Freuden
    -0.52
    Ranks
    -0.49
     Stande
    -0.49
    kmal
    -0.48
    Ữ
    -0.47
    hema
    -0.47
    arem
    -0.46
     unexplo
    -0.45
    bito
    -0.45
    ốt
    -0.45
    POSITIVE LOGITS
     constantly
    0.85
    throughout
    0.74
     continually
    0.73
     kept
    0.72
    DockStyle
    0.70
    ArgsConstructor
    0.70
     meanwhile
    0.70
     continuously
    0.70
     throughout
    0.70
     alternately
    0.70
    Act Density 0.393%

    No Known Activations