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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the continual aspect of actions or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing consistency and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.79
    rig
    -0.73
    DF
    -0.72
    IDA
    -0.71
    iants
    -0.69
     Kardashian
    -0.68
    lations
    -0.68
     DAC
    -0.68
    SG
    -0.68
    åĤ
    -0.68
    POSITIVE LOGITS
    theless
    0.91
    entimes
    0.89
     dreamed
    0.79
     appreciated
    0.79
     overlooked
    0.78
     lurking
    0.76
     evolving
    0.75
     fascinated
    0.75
     thereafter
    0.74
     bothered
    0.74
    Act Density 0.037%

    No Known Activations