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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a particular format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intersper
    -0.71
     gaily
    -0.69
     tolerably
    -0.68
     unspeak
    -0.67
     disagre
    -0.65
     beaute
    -0.65
     apprehen
    -0.63
     friable
    -0.63
     shenan
    -0.59
     gratify
    -0.58
    POSITIVE LOGITS
     ideolog
    0.66
     meras
    0.64
     sedia
    0.61
     solidar
    0.60
     maksi
    0.58
     notor
    0.54
     alkoh
    0.54
     robus
    0.53
     verdura
    0.53
     nastro
    0.52
    Act Density 0.073%

    No Known Activations