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

    Neuronpedia

    INDEX
    Explanations

    terms related to various types of organizational divisions or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (s
    -0.18
    aceous
    -0.18
    Ñıл
    -0.16
    shi
    -0.16
    EMPLARY
    -0.15
    bero
    -0.15
    stown
    -0.15
    anguages
    -0.15
    eam
    -0.15
    å®Ļ
    -0.15
    POSITIVE LOGITS
    (es
    0.59
    s
    0.47
    es
    0.40
    y
    0.36
    er
    0.33
    ers
    0.32
    ES
    0.31
    sing
    0.29
    ses
    0.29
    erman
    0.28
    Act Density 0.174%

    No Known Activations