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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical conditioning

    oai_token-act-pair · gpt-3.5-turbo

    references to conditioning in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enic
    -0.86
    pg
    -0.77
    uru
    -0.71
    gil
    -0.69
    SN
    -0.68
    zag
    -0.67
    meet
    -0.66
    athan
    -0.66
    arrow
    -0.65
    zl
    -0.65
    POSITIVE LOGITS
     conditioning
    1.41
     conditioned
    1.28
     confir
    1.23
     destro
    1.09
     veter
    1.02
     streng
    0.98
     occas
    0.96
     exha
    0.94
     therap
    0.93
     disadvant
    0.93
    Act Density 0.011%

    No Known Activations