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

    Neuronpedia

    INDEX
    Explanations

    terms related to artifacts in various contexts

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

    artifact, ArtifactSet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.52
    Hochspringen
    -0.48
    المناصب
    -0.47
     InputDecoration
    -0.47
    ConstraintMaker
    -0.46
    бият
    -0.44
    thenReturn
    -0.43
    Читайте
    -0.43
    Autoritní
    -0.43
    )<\
    -0.42
    POSITIVE LOGITS
     artifact
    2.09
     artifacts
    2.03
     Artifact
    1.85
     Artifacts
    1.80
    artifact
    1.79
    Artifact
    1.78
    artifacts
    1.77
    Artifacts
    1.68
     artefacts
    1.63
     arte
    1.41
    Act Density 0.004%

    No Known Activations