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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or activities that involve consequences or commitments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -1.09
    urers
    -0.70
    encers
    -0.68
     Survivors
    -0.67
     sponsors
    -0.66
    etheless
    -0.65
     dudes
    -0.65
    mates
    -0.65
    resses
    -0.64
    enta
    -0.63
    POSITIVE LOGITS
     duties
    0.86
     coup
    0.85
     tasks
    0.85
     manoeuv
    0.85
     unilateral
    0.84
     abl
    0.84
     ritual
    0.84
     bidding
    0.84
     utmost
    0.83
     rituals
    0.82
    Act Density 0.278%

    No Known Activations