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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or conditions related to expectations and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ady
    -0.17
    dal
    -0.15
     repetition
    -0.15
    lingen
    -0.15
    ignon
    -0.14
    andas
    -0.14
    opper
    -0.14
    ude
    -0.14
    žel
    -0.14
    iti
    -0.13
    POSITIVE LOGITS
    'gc
    0.16
    æĸĻ
    0.15
    esModule
    0.15
    slt
    0.15
    ystate
    0.14
    streams
    0.14
    presso
    0.14
    arov
    0.14
    DefaultValue
    0.14
    sono
    0.14
    Act Density 0.003%

    No Known Activations