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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a potential action or consequence

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements indicating consequences or situations dependent on specific criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eye
    -0.74
    ãĤª
    -0.72
    Poké
    -0.66
    akia
    -0.66
    yss
    -0.64
     Roses
    -0.64
    oult
    -0.64
    âĸĪâĸĪâĸĪâĸĪ
    -0.63
    kins
    -0.62
    Arm
    -0.61
    POSITIVE LOGITS
    fy
    0.97
    rame
    0.97
    ornia
    0.85
     necessary
    0.82
    soever
    0.80
     they
    0.80
     you
    0.69
     warranted
    0.66
     unchecked
    0.66
    culosis
    0.66
    Act Density 0.070%

    No Known Activations