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

    Neuronpedia

    INDEX
    Explanations

    words related to triggering or causing events or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ties
    -0.15
    ãĥ¼ãĥ³
    -0.14
    clipse
    -0.14
    sie
    -0.14
    ikt
    -0.14
    ä½į
    -0.14
    wig
    -0.14
    Refreshing
    -0.13
     subt
    -0.13
    iser
    -0.13
    POSITIVE LOGITS
    63
    0.16
    oftware
    0.16
    235
    0.15
    ingly
    0.15
    znik
    0.15
     Lloyd
    0.14
    MDB
    0.14
    inel
    0.14
    -response
    0.14
    ëĤĺ무
    0.14
    Act Density 0.087%

    No Known Activations