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

    Neuronpedia

    INDEX
    Explanations

    phrases related to profit or benefit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "prof" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warm
    -0.69
    WARE
    -0.67
    forth
    -0.65
    MENTS
    -0.64
     shortened
    -0.64
     halfway
    -0.64
     coupled
    -0.64
    WAY
    -0.62
    WAYS
    -0.62
    âĶĢâĶĢâĶĢâĶĢ
    -0.59
    POSITIVE LOGITS
    iled
    1.35
    iler
    1.33
    anity
    1.29
    ilers
    1.25
    iles
    1.21
    iling
    1.19
    essor
    1.17
    usion
    1.15
    aned
    1.14
    ession
    1.14
    Act Density 0.016%

    No Known Activations