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

    Neuronpedia

    INDEX
    Explanations

    terms related to introducing or presenting new products or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ania
    -0.16
    anity
    -0.16
    adro
    -0.16
    angent
    -0.15
    aniu
    -0.15
    (PHP
    -0.14
    iva
    -0.14
    ardo
    -0.14
    ilden
    -0.14
     Miscellaneous
    -0.14
    POSITIVE LOGITS
    OrElse
    0.15
    iterated
    0.15
    corner
    0.14
    emachine
    0.14
    gba
    0.14
    Drag
    0.14
    ammad
    0.14
    stal
    0.14
    ycin
    0.14
     Drag
    0.13
    Act Density 0.006%

    No Known Activations