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

    Neuronpedia

    INDEX
    Explanations

    words expressing strong opinions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymb
    -0.17
     Rank
    -0.15
    âr
    -0.15
     invit
    -0.15
    945
    -0.14
    änn
    -0.14
    oga
    -0.14
    ør
    -0.14
     Calendar
    -0.14
    uppy
    -0.14
    POSITIVE LOGITS
     words
    0.18
    ighton
    0.16
    _words
    0.15
     WORD
    0.14
     Thema
    0.14
    _WORDS
    0.14
    adeon
    0.14
     word
    0.14
    ÎĨ
    0.14
    words
    0.14
    Act Density 0.068%

    No Known Activations