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

    Neuronpedia

    INDEX
    Explanations

    expressions related to uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.49
     kaarangay
    -0.45
    뀜
    -0.42
     matching
    -0.41
    matching
    -0.40
    pecto
    -0.39
    Matching
    -0.39
     correcto
    -0.39
    agaimana
    -0.38
     bené
    -0.37
    POSITIVE LOGITS
    principalColumn
    0.52
    UnusedPrivate
    0.50
    keyColumn
    0.49
    IntoConstraints
    0.47
    jamientos
    0.47
     initWithFrame
    0.45
     invokingState
    0.45
    AnimationsModule
    0.45
    ➟
    0.44
    RTEX
    0.44
    Act Density 1.188%

    No Known Activations