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

    Neuronpedia

    INDEX
    Explanations

    references to specific categories or sectors, particularly related to art or cultural expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alist
    -0.16
    yll
    -0.16
    ilty
    -0.15
    aggable
    -0.15
    IGGER
    -0.15
    furt
    -0.15
    ely
    -0.15
    atatype
    -0.15
    enance
    -0.14
    altung
    -0.14
    POSITIVE LOGITS
    leg
    0.20
    lege
    0.19
    lect
    0.19
    loor
    0.18
    LECT
    0.17
    _wheel
    0.17
    abor
    0.17
     minh
    0.16
    league
    0.16
    cas
    0.16
    Act Density 0.011%

    No Known Activations