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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal qualities or behaviors, such as credit, surprise, delight, dismay, estimates, standards, calculations, indications, accounts, and witness

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing notions of credit and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roleum
    -0.69
    NetMessage
    -0.69
    rete
    -0.68
    ente
    -0.67
    scribe
    -0.67
    fix
    -0.65
    itive
    -0.64
    vir
    -0.63
    rir
    -0.63
    ute
    -0.59
    POSITIVE LOGITS
    ij士
    0.65
    Sham
    0.63
     hindsight
    0.62
     admission
    0.61
     backups
    0.59
     agility
    0.58
     instincts
    0.57
     subordinates
    0.57
     Wasserman
    0.57
    urances
    0.56
    Act Density 0.092%

    No Known Activations