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

    Neuronpedia

    INDEX
    Explanations

    modal verbs that indicate possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rella
    -0.18
    isclosed
    -0.16
    =default
    -0.15
    §
    -0.15
     CreateMap
    -0.15
    δα
    -0.14
    aign
    -0.14
    ioni
    -0.14
    timeofday
    -0.14
    æ¥ļ
    -0.14
    POSITIVE LOGITS
     accommod
    0.23
     accommodate
    0.23
     accom
    0.19
     fit
    0.19
     satisfied
    0.17
    iron
    0.17
     fitting
    0.17
     cater
    0.16
    Fit
    0.16
     Satisfaction
    0.16
    Act Density 0.011%

    No Known Activations