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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and changes in conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wn
    -0.15
    umbs
    -0.15
    _STMT
    -0.15
     |_|
    -0.15
    anh
    -0.14
    ownt
    -0.14
    ucer
    -0.14
    nze
    -0.14
     Stmt
    -0.14
    392
    -0.13
    POSITIVE LOGITS
    onas
    0.18
     forwards
    0.15
    ibo
    0.14
     splash
    0.14
    ней
    0.14
    hood
    0.14
    ieri
    0.14
    inha
    0.14
    ACKET
    0.14
    foon
    0.14
    Act Density 0.080%

    No Known Activations