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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to electronic devices and components

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to technology and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à©
    -0.69
    à¨
    -0.67
    psy
    -0.65
    IENT
    -0.63
    ISH
    -0.61
     circumstance
    -0.60
     diversion
    -0.60
     VID
    -0.59
     distraction
    -0.59
    beat
    -0.58
    POSITIVE LOGITS
    hips
    1.39
    hip
    1.16
    etter
    1.14
    paces
    1.05
    poons
    1.04
    uggest
    1.04
    ilver
    1.04
    chool
    1.01
    hops
    0.99
    heet
    0.96
    Act Density 0.620%

    No Known Activations