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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate outcomes or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wine
    -0.68
     outset
    -0.64
    STER
    -0.63
     tucked
    -0.61
    MEN
    -0.61
    Link
    -0.59
     playbook
    -0.59
    dated
    -0.59
    lite
    -0.58
    timer
    -0.58
    POSITIVE LOGITS
    escap
    0.77
    ordinate
    0.74
    illions
    0.72
    clusions
    0.72
    ushima
    0.69
    effic
    0.69
    aba
    0.68
    ãĥĩãĤ£
    0.67
    pletion
    0.66
     either
    0.65
    Act Density 0.045%

    No Known Activations