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

    Neuronpedia

    INDEX
    Explanations

    \it phrases or sentences describing something in detail

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "describe" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.81
    acus
    -0.80
    ublic
    -0.69
    umo
    -0.67
    nown
    -0.67
    aghetti
    -0.66
    iasm
    -0.65
    atri
    -0.64
    sei
    -0.63
     Sabha
    -0.63
    POSITIVE LOGITS
     descriptions
    0.98
     describ
    0.85
    REDACTED
    0.78
    urally
    0.76
     describes
    0.74
    urated
    0.74
     describing
    0.71
     describe
    0.70
    Filename
    0.70
    ively
    0.69
    Act Density 0.019%

    No Known Activations