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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outcomes, especially whether things succeed or fail

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the success or failure of efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewitness
    -0.79
    pora
    -0.69
    erity
    -0.68
    quartered
    -0.68
    quin
    -0.67
    ership
    -0.66
    idi
    -0.66
    inflamm
    -0.65
    den
    -0.65
    ritical
    -0.65
    POSITIVE LOGITS
     miser
    1.01
     spectacular
    0.89
     satisf
    0.84
     smoothly
    0.82
     horribly
    0.79
     dividends
    0.78
     disastrous
    0.76
     favour
    0.75
     fruition
    0.74
     favor
    0.73
    Act Density 0.153%

    No Known Activations