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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing events, developments, or changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant developments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rients
    -0.71
    usercontent
    -0.70
    ulner
    -0.69
     brakes
    -0.66
     residues
    -0.65
     outweigh
    -0.65
    odied
    -0.64
    hyde
    -0.64
     PTS
    -0.63
    onents
    -0.63
    POSITIVE LOGITS
     coincidence
    0.72
    urai
    0.71
    ãĥĪ
    0.70
     nutshell
    0.69
     understatement
    0.69
     perverse
    0.67
     reversal
    0.63
     precaution
    0.63
     ironic
    0.63
     irony
    0.63
    Act Density 0.266%

    No Known Activations