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

    Neuronpedia

    INDEX
    Explanations

    ambiguous or irrelevant content, as there is no consistent theme or pattern in the activations

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases or references to entities associated with style or behavior in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <@
    -0.70
     gib
    -0.68
     Gmail
    -0.66
     decomp
    -0.66
     "+
    -0.65
     JPEG
    -0.65
     +++
    -0.64
     scrut
    -0.61
     fortun
    -0.61
     "<
    -0.61
    POSITIVE LOGITS
    s
    1.53
    ski
    1.10
    scl
    1.05
    ses
    1.02
    ship
    1.02
    t
    1.02
    d
    0.98
    ved
    0.97
    tis
    0.97
    tal
    0.95
    Act Density 0.338%

    No Known Activations