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

    Neuronpedia

    INDEX
    Explanations

    terms related to publishing and editorial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.17
    ivor
    -0.16
     pec
    -0.15
    zos
    -0.14
    undy
    -0.14
    ivol
    -0.14
    428
    -0.14
     cler
    -0.13
    idor
    -0.13
    rone
    -0.13
    POSITIVE LOGITS
    ichen
    0.15
    angi
    0.15
    _SOFT
    0.14
    enne
    0.14
    pat
    0.13
    osten
    0.13
    .requires
    0.13
    een
    0.13
    adden
    0.13
    uild
    0.13
    Act Density 0.005%

    No Known Activations