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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.76
    DEV
    -0.69
     rodents
    -0.66
    aepernick
    -0.65
    expression
    -0.65
     surg
    -0.64
     depress
    -0.63
    berman
    -0.62
    gging
    -0.62
     lucky
    -0.62
    POSITIVE LOGITS
    ith
    1.37
    otle
    1.06
    iths
    1.00
    ium
    0.97
    ieth
    0.92
    yll
    0.92
    iop
    0.87
    ACA
    0.82
    ofer
    0.81
    ITH
    0.80
    Act Density 0.009%

    No Known Activations