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

    Neuronpedia

    INDEX
    Explanations

    words related to technical operations and connections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iPhone
    -0.64
    izer
    -0.64
    IU
    -0.62
    Invalid
    -0.62
    ider
    -0.61
    fur
    -0.60
    imus
    -0.60
    iste
    -0.59
    izers
    -0.59
    ãĥ£
    -0.58
    POSITIVE LOGITS
     secondly
    0.85
    ersen
    0.80
     furthermore
    0.77
    rew
    0.77
     finally
    0.77
     alternatively
    0.75
    oros
    0.70
    romeda
    0.68
     consequently
    0.65
    ortunately
    0.65
    Act Density 0.092%

    No Known Activations