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

    Neuronpedia

    INDEX
    Explanations

    phrases where something is defined or categorized

    oai_token-act-pair · gpt-3.5-turbo

    the word "defined" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osc
    -0.74
    eor
    -0.72
    atl
    -0.72
    heastern
    -0.70
    folio
    -0.70
    ersen
    -0.69
    rone
    -0.69
    rax
    -0.69
    orate
    -0.67
    rol
    -0.67
    POSITIVE LOGITS
     follows
    0.97
    pired
    0.84
     opposed
    0.81
    pires
    0.78
     well
    0.77
    ocial
    0.75
     favoring
    0.74
    criptions
    0.74
     belonging
    0.73
    ylum
    0.73
    Act Density 0.100%

    No Known Activations