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

    Neuronpedia

    INDEX
    Explanations

    classifications and types within various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emble
    -0.16
    atives
    -0.14
    wer
    -0.14
    xt
    -0.14
     twins
    -0.13
    ail
    -0.13
    layan
    -0.13
    amet
    -0.13
    nant
    -0.13
    ifo
    -0.13
    POSITIVE LOGITS
     types
    0.22
     Types
    0.18
    -types
    0.18
     Options
    0.16
    Types
    0.15
    adia
    0.15
    ocz
    0.15
    TYPES
    0.15
    types
    0.15
     options
    0.15
    Act Density 0.300%

    No Known Activations