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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of withdrawing support or participation

    oai_token-act-pair · gpt-3.5-turbo

    references to support or participation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ingenious
    -0.66
    auld
    -0.66
    iewicz
    -0.65
     shrew
    -0.64
    ipel
    -0.64
    olic
    -0.63
    positive
    -0.61
    lav
    -0.61
    ric
    -0.59
    ymph
    -0.58
    POSITIVE LOGITS
     altogether
    1.51
     entirely
    1.09
     prematurely
    0.97
     anymore
    0.89
     indefinitely
    0.87
     abruptly
    0.85
     outright
    0.80
    ãĤ®
    0.80
     inhib
    0.79
     due
    0.79
    Act Density 0.380%

    No Known Activations