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

    Neuronpedia

    INDEX
    Explanations

    words related to actions of going back and forth

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    panel
    -0.77
    ongo
    -0.74
    cess
    -0.69
    ebted
    -0.67
    successful
    -0.66
    behavior
    -0.65
    riad
    -0.65
    anz
    -0.63
    uses
    -0.63
    ancial
    -0.62
    POSITIVE LOGITS
    rogen
    0.77
     THEN
    0.76
     vo
    0.73
     begged
    0.72
     hopefully
    0.71
     forth
    0.70
    rogens
    0.69
    romeda
    0.69
     congratulate
    0.66
     let
    0.66
    Act Density 0.177%

    No Known Activations