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

    Neuronpedia

    INDEX
    Explanations

    phrases related to desires or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to personal desires or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Notting
    -0.75
    :{
    -0.65
     coli
    -0.64
     istg
    -0.64
     Function
    -0.62
    /
    -0.62
     anecd
    -0.59
     Grounds
    -0.58
    wald
    -0.58
    umbered
    -0.57
    POSITIVE LOGITS
     sake
    0.76
    thood
    0.74
     realism
    0.70
    reprene
    0.67
     daddy
    0.66
     forgiveness
    0.65
    unic
    0.64
    cest
    0.64
    iency
    0.64
     clarity
    0.63
    Act Density 0.257%

    No Known Activations