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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or concern

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate significance, concern, and interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.74
    odd
    -0.68
    hell
    -0.67
    ammy
    -0.67
    aah
    -0.66
     Masquerade
    -0.61
     Cancel
    -0.60
    akedown
    -0.60
    ynthesis
    -0.58
     cond
    -0.58
    POSITIVE LOGITS
     è£ıè
    0.79
    é¾įå¥ij士
    0.72
    Reviewer
    0.67
    EStream
    0.65
    marks
    0.63
     internationally
    0.62
     because
    0.62
    chery
    0.62
    0000000
    0.61
     guiActiveUn
    0.60
    Act Density 0.131%

    No Known Activations