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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of solidarity or shared experience

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alone" and related phrases indicating solitude or lack of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imal
    -0.70
     GENERAL
    -0.69
    VERTISEMENT
    -0.65
    inders
    -0.64
    ffff
    -0.64
    mun
    -0.62
     decay
    -0.61
    chlor
    -0.61
    wash
    -0.60
    mit
    -0.59
    POSITIVE LOGITS
    arus
    0.79
     culp
    0.71
    odox
    0.67
     academ
    0.66
    ta
    0.65
    gebra
    0.64
     exoner
    0.63
     apprehens
    0.63
    isSpecialOrderable
    0.62
    MpServer
    0.61
    Act Density 0.020%

    No Known Activations