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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various ways of doing things or taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to means and methods of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    livious
    -0.82
    head
    -0.81
    roth
    -0.70
    heads
    -0.65
    llah
    -0.64
     Roller
    -0.63
    clair
    -0.61
    rollment
    -0.60
    ATOR
    -0.60
    abad
    -0.59
    POSITIVE LOGITS
     practicable
    1.31
     possible
    1.24
     necessary
    1.20
     feasible
    1.12
     appropriate
    1.11
     desired
    1.10
    necessary
    1.06
     reasonably
    0.95
     imaginable
    0.93
     needed
    0.93
    Act Density 0.524%

    No Known Activations