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

    Neuronpedia

    INDEX
    Explanations

    terms associated with physical structures and concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelProperty
    -0.16
    amma
    -0.15
    inux
    -0.15
    estroy
    -0.15
    conv
    -0.14
    avanaugh
    -0.14
    ovel
    -0.14
    oppable
    -0.14
    angent
    -0.14
    端
    -0.14
    POSITIVE LOGITS
    afil
    0.17
    recision
    0.15
    siyon
    0.14
    opa
    0.14
    esan
    0.14
    _UD
    0.14
     wholes
    0.14
    OLOR
    0.14
    bite
    0.14
     Essential
    0.13
    Act Density 0.449%

    No Known Activations