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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships and actions involving "someone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.82
    DOS
    -0.74
    tnc
    -0.67
    veyard
    -0.67
    osterone
    -0.66
    enegger
    -0.63
    heny
    -0.62
    letters
    -0.62
    HL
    -0.59
    Plex
    -0.58
    POSITIVE LOGITS
     else
    2.10
    else
    1.43
    Else
    1.31
     Else
    1.23
     who
    1.08
     whom
    0.93
     whose
    0.88
    who
    0.85
    's
    0.79
     EL
    0.73
    Act Density 0.069%

    No Known Activations