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

    Neuronpedia

    INDEX
    Explanations

    concepts related to accountability and rules within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INFRINGEMENT
    -0.17
    alue
    -0.15
    peg
    -0.15
    cond
    -0.14
    iron
    -0.14
    gether
    -0.14
    dest
    -0.14
    manual
    -0.14
    cly
    -0.13
    WEEN
    -0.13
    POSITIVE LOGITS
    S
    1.05
    SJ
    0.47
    s
    0.44
    SX
    0.42
    ÂłS
    0.36
    SZ
    0.36
    SF
    0.34
    SU
    0.31
    SAM
    0.31
    Sz
    0.30
    Act Density 0.168%

    No Known Activations