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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high level of performance or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common experiences or situations related to societal norms and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lav
    -0.82
    yond
    -0.80
    aba
    -0.78
    rig
    -0.77
    imar
    -0.76
    ipl
    -0.74
    azel
    -0.74
    amic
    -0.74
    ollo
    -0.73
    ulu
    -0.73
    POSITIVE LOGITS
     athlet
    0.69
     offensively
    0.66
     applause
    0.66
     financially
    0.66
     academ
    0.63
     understatement
    0.61
     mascara
    0.60
    .
    0.60
     speculation
    0.59
     beaut
    0.58
    Act Density 0.540%

    No Known Activations