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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    statements of commitment or promises made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äºĶ
    -0.71
    nesota
    -0.70
    æѦ
    -0.69
    elaide
    -0.68
    iquid
    -0.68
    Occ
    -0.67
    ateral
    -0.67
    intage
    -0.66
    iddling
    -0.65
    aptop
    -0.64
    POSITIVE LOGITS
     vow
    0.90
    lessly
    0.84
     vows
    0.81
    lessness
    0.79
     anew
    0.73
     defiant
    0.71
     allegiance
    0.71
    ggle
    0.69
    rely
    0.68
     oath
    0.68
    Act Density 0.027%

    No Known Activations