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

    Neuronpedia

    INDEX
    Explanations

    text encased in special characters, possibly related to online profiles or forums

    oai_token-act-pair · gpt-3.5-turbo

    instances of user profiles and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undermin
    -0.69
     dotted
    -0.68
     principals
    -0.66
     flee
    -0.64
     princ
    -0.63
     multiplication
    -0.62
     corpus
    -0.62
     purs
    -0.62
     mosqu
    -0.61
     dads
    -0.60
    POSITIVE LOGITS
     guiName
    0.89
    Show
    0.85
    https
    0.81
    Member
    0.77
    Thread
    0.75
    Reply
    0.75
    uin
    0.75
    =-=-=-=-=-=-=-=-
    0.73
    Gam
    0.71
    any
    0.71
    Act Density 0.103%

    No Known Activations