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

    Neuronpedia

    INDEX
    Explanations

    abbreviations related to management or training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosper
    -0.19
    ãĥĥãĥĦ
    -0.16
    ãĥĥ
    -0.16
    itzer
    -0.15
    msp
    -0.14
    ç£
    -0.14
    ibo
    -0.14
    NotNull
    -0.14
    ray
    -0.13
     Armour
    -0.13
    POSITIVE LOGITS
    ',...↵
    0.16
    amba
    0.15
    dition
    0.15
    esson
    0.14
    ÏĦζ
    0.14
    ldb
    0.14
    uy
    0.13
    ice
    0.13
    '&&
    0.13
    综åIJĪ
    0.13
    Act Density 0.004%

    No Known Activations