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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    expressions concerning the requirement or effort needed to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luster
    -0.68
    etheless
    -0.67
    ateg
    -0.66
    ahime
    -0.66
     agre
    -0.65
    Ń·
    -0.65
    arbon
    -0.64
    \\\\\\\\
    -0.64
    idden
    -0.64
     convol
    -0.62
    POSITIVE LOGITS
     to
    1.03
    to
    0.79
     TO
    0.75
     ta
    0.72
     To
    0.69
    TO
    0.61
    To
    0.61
     unto
    0.59
    IENCE
    0.56
     for
    0.56
    Act Density 0.088%

    No Known Activations