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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases and references to specific cases or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tober
    -0.16
    Ctrls
    -0.15
    _Surface
    -0.14
    ÙĦÛĮÙĦ
    -0.14
    ÙĩÙħ
    -0.14
    893
    -0.14
    arges
    -0.13
    tainment
    -0.13
    ầm
    -0.13
     COLORS
    -0.13
    POSITIVE LOGITS
     case
    0.49
     cases
    0.46
     event
    0.43
     instances
    0.41
     rare
    0.40
    case
    0.39
     instance
    0.38
     caso
    0.36
    cases
    0.35
    event
    0.34
    Act Density 0.191%

    No Known Activations