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

    Neuronpedia

    INDEX
    Explanations

    website links or mentions of authors and publications

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters or codes, particularly alphanumeric strings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.70
     Levant
    -0.68
    anwhile
    -0.67
     destro
    -0.65
     rall
    -0.65
     tradem
    -0.65
     conflic
    -0.65
    Orderable
    -0.64
     tremend
    -0.62
     sidx
    -0.62
    POSITIVE LOGITS
    /)
    0.98
    /?
    0.93
    bg
    0.89
    /,
    0.87
    014
    0.85
    bb
    0.85
    201
    0.81
    /.
    0.80
    pb
    0.80
    __
    0.79
    Act Density 0.074%

    No Known Activations