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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing or commenting on a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate further information or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obook
    -0.69
    chieve
    -0.64
    enance
    -0.64
    irlf
    -0.61
    assadors
    -0.60
    ebted
    -0.58
    ierrez
    -0.57
     Opposition
    -0.57
     parap
    -0.56
    ifts
    -0.55
    POSITIVE LOGITS
    eeee
    0.70
     disapp
    0.67
     ya
    0.65
     awfully
    0.65
     alright
    0.64
     caveat
    0.64
     semantics
    0.62
     ASAP
    0.62
     kinda
    0.62
     dude
    0.61
    Act Density 0.591%

    No Known Activations