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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hobbies or interests

    oai_token-act-pair · gpt-3.5-turbo

    words that denote enthusiasts or supporters of specific interests or subcultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrang
    -0.67
    usable
    -0.63
    inventoryQuantity
    -0.59
     Payments
    -0.59
     executions
    -0.59
     bilateral
    -0.59
    ptroller
    -0.58
    ONSORED
    -0.58
    Hig
    -0.57
    ictional
    -0.56
    POSITIVE LOGITS
     rejoice
    1.61
     alike
    1.44
     beware
    1.36
     everywhere
    1.16
     extraord
    1.08
     flock
    1.01
     who
    0.92
    peak
    0.89
     wanting
    0.86
     wishing
    0.86
    Act Density 0.209%

    No Known Activations