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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases conveying positive experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kins
    -0.16
    /read
    -0.15
    stÅĻed
    -0.15
    /remove
    -0.15
    onica
    -0.14
    avr
    -0.14
    .spi
    -0.14
    Reuse
    -0.14
    FRING
    -0.14
    ridge
    -0.14
    POSITIVE LOGITS
    656
    0.16
    /testing
    0.15
    -dir
    0.14
    atak
    0.14
    546
    0.14
     Ket
    0.14
     inflation
    0.13
     lately
    0.13
     NOW
    0.13
    706
    0.13
    Act Density 0.800%

    No Known Activations