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

    Neuronpedia

    INDEX
    Explanations

    claims or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements of belief or fact made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrang
    -0.81
     Watching
    -0.72
    thumbnails
    -0.66
     merc
    -0.66
     guiActiveUnfocused
    -0.65
    cephal
    -0.64
     Selected
    -0.62
    committee
    -0.62
    lite
    -0.61
     heartbeat
    -0.61
    POSITIVE LOGITS
    edly
    0.74
    ulence
    0.73
     claims
    0.69
     deductions
    0.69
    uca
    0.69
     asylum
    0.67
    ril
    0.66
    ifications
    0.66
    icist
    0.66
    ayn
    0.66
    Act Density 0.039%

    No Known Activations