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

    Neuronpedia

    INDEX
    Explanations

    words related to challenges or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAR
    -0.69
    asus
    -0.68
    Mos
    -0.64
    APTER
    -0.62
     VID
    -0.62
     Citiz
    -0.61
    ãĥ£
    -0.61
    ENG
    -0.60
    \\\\\\\\
    -0.60
    ¾
    -0.59
    POSITIVE LOGITS
    pring
    1.14
    hip
    1.12
    ettings
    1.11
    hips
    1.10
    hare
    1.09
    uggest
    1.08
    hooting
    1.08
    omething
    1.07
    mith
    1.07
    uits
    1.06
    Act Density 0.210%

    No Known Activations