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

    Neuronpedia

    INDEX
    Explanations

    references to where information or items can be located

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating discovery or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assisted
    -0.82
    istry
    -0.76
    aired
    -0.69
     bailed
    -0.67
    stroke
    -0.66
    rons
    -0.65
    airs
    -0.64
    commit
    -0.63
     cannabin
    -0.62
    EStreamFrame
    -0.61
    POSITIVE LOGITS
    èĢħ
    0.86
     plenty
    0.85
    ãĤ¤ãĥĪ
    0.81
    upon
    0.80
    ¶æ
    0.78
    çīĪ
    0.74
    女
    0.73
     attractive
    0.72
    ãĤĮ
    0.72
     yourself
    0.71
    Act Density 0.060%

    No Known Activations