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

    Neuronpedia

    INDEX
    Explanations

    verb phrases related to completing tasks or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to processes involving completion or finalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Magikarp
    -0.76
    ONSORED
    -0.72
     predators
    -0.65
     lesbians
    -0.63
     cafes
    -0.61
     tabl
    -0.60
     TVs
    -0.59
    resses
    -0.59
     mounts
    -0.58
     bullies
    -0.58
    POSITIVE LOGITS
     satisf
    0.84
    issance
    0.81
     cycle
    0.78
     captcha
    0.78
    ecycle
    0.76
     journey
    0.76
    requisites
    0.74
    auntlet
    0.74
     tasks
    0.74
     prepar
    0.72
    Act Density 0.185%

    No Known Activations