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

    Neuronpedia

    INDEX
    Explanations

    terms related to limitations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ated
    -0.61
    ized
    -0.54
    ened
    -0.47
    äºĨ
    -0.47
    ified
    -0.42
    ged
    -0.38
    ATED
    -0.28
    ured
    -0.27
    ished
    -0.26
    IZED
    -0.25
    POSITIVE LOGITS
    äºĨä¸Ģ
    0.28
    ised
    0.23
    atedRoute
    0.21
    izedName
    0.18
    глÑıд
    0.18
    yth
    0.16
    apesh
    0.15
    ØŃÙĨ
    0.15
    .logical
    0.14
    -Saharan
    0.14
    Act Density 0.119%

    No Known Activations