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

    Neuronpedia

    INDEX
    Explanations

    expressions of categorization or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onders
    -0.17
    OOM
    -0.16
    eus
    -0.15
    ensible
    -0.15
    ulton
    -0.15
    ancellable
    -0.15
    IDES
    -0.15
    NÄ°
    -0.15
    trap
    -0.15
    eniable
    -0.15
    POSITIVE LOGITS
    've
    0.31
    da
    0.28
    ve
    0.28
    ’ve
    0.26
    a
    0.26
    'a
    0.25
    ta
    0.24
    uv
    0.22
    ove
    0.21
    ’a
    0.20
    Act Density 0.013%

    No Known Activations