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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the word "acht" and its variations, likely indicating a focus on the theme of "eight" or related concepts in a textual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.87
    ourke
    -0.81
    ãģ¦
    -0.79
     Gleaming
    -0.77
    culus
    -0.76
    ces
    -0.74
    yip
    -0.73
    gur
    -0.73
    culation
    -0.73
    ce
    -0.72
    POSITIVE LOGITS
    alion
    1.06
    rop
    0.88
    mann
    0.87
    ronics
    0.85
    ract
    0.84
    iller
    0.82
    geist
    0.80
    rieg
    0.80
    rust
    0.78
    ung
    0.77
    Act Density 0.016%

    No Known Activations