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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "go" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -0.17
    /un
    -0.15
    ised
    -0.14
    sein
    -0.14
    cular
    -0.14
    xes
    -0.14
    arians
    -0.14
    uite
    -0.14
    teen
    -0.13
    med
    -0.13
    POSITIVE LOGITS
    -away
    0.16
    adget
    0.15
    нез
    0.15
    alic
    0.14
    esh
    0.14
    AMA
    0.13
    gere
    0.13
    chas
    0.13
    OGLE
    0.13
    age
    0.13
    Act Density 0.162%

    No Known Activations