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

    Neuronpedia

    INDEX
    Explanations

    terms of endearment

    oai_token-act-pair · gpt-3.5-turbo

    terms of endearment or affectionate descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.85
    ammers
    -0.79
    NetMessage
    -0.76
    ulhu
    -0.75
    IDER
    -0.73
    hner
    -0.68
    anwhile
    -0.67
    ept
    -0.67
     largeDownload
    -0.66
    DEBUG
    -0.65
    POSITIVE LOGITS
     dear
    1.23
     dearly
    0.92
     acquaintance
    0.82
     friend
    0.75
    born
    0.75
     departed
    0.74
     hearts
    0.74
     friends
    0.73
     Esther
    0.72
    iors
    0.71
    Act Density 0.010%

    No Known Activations