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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and structures in data representation or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Collect the terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.48
    <bos>
    -0.47
    ✨:
    -0.44
     itſelf
    -0.43
     Preferencias
    -0.42
     ModelExpression
    -0.42
     Entwicklungs
    -0.42
     обстоя
    -0.41
    WriteTagHelper
    -0.41
     ProtoMessage
    -0.40
    POSITIVE LOGITS
    abstractmethod
    0.49
     consultato
    0.46
    idiot
    0.41
    truc
    0.40
    øb
    0.40
     coke
    0.40
     squat
    0.40
     cocker
    0.40
     blunt
    0.40
    ursos
    0.39
    Act Density 0.283%

    No Known Activations