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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a search for information or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsey
    -0.18
    į°
    -0.15
    enate
    -0.15
    quate
    -0.15
    inize
    -0.15
    ropoda
    -0.14
    uddy
    -0.14
    chine
    -0.14
    velop
    -0.13
     kang
    -0.13
    POSITIVE LOGITS
     whether
    0.17
     about
    0.17
    itor
    0.15
    æijĦ
    0.14
     how
    0.14
    aket
    0.14
     why
    0.14
    ctors
    0.14
    braco
    0.14
    _about
    0.14
    Act Density 0.012%

    No Known Activations