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

    Neuronpedia

    INDEX
    Explanations

    words related to expressions of love and care

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love and care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.84
    inates
    -0.78
    obyl
    -0.70
    */(
    -0.68
    ngth
    -0.67
    VEL
    -0.66
     Lans
    -0.65
    classified
    -0.64
    Ultra
    -0.63
    ibrary
    -0.63
    POSITIVE LOGITS
    tons
    0.83
     adoptive
    0.74
     beings
    0.73
     kindness
    0.70
     altru
    0.69
    minded
    0.69
    glers
    0.69
     minded
    0.69
    itar
    0.68
    ton
    0.65
    Act Density 0.052%

    No Known Activations