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

    Neuronpedia

    INDEX
    Explanations

    references to toys and play-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inos
    -0.18
    ader
    -0.16
    phans
    -0.15
    996
    -0.15
    ned
    -0.15
    ÑĢо
    -0.14
    odzi
    -0.14
    बर
    -0.14
    vert
    -0.14
    272
    -0.13
    POSITIVE LOGITS
    å½
    0.15
     toys
    0.15
    istic
    0.15
     toy
    0.15
    angan
    0.15
    111
    0.14
    egin
    0.14
    CDATA
    0.14
    istically
    0.14
     Trafford
    0.14
    Act Density 0.013%

    No Known Activations