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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various factors influencing different situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or lists of factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.80
    iaries
    -0.75
    ogun
    -0.72
    thren
    -0.71
    rift
    -0.71
    okane
    -0.69
    lees
    -0.68
    oir
    -0.67
    ath
    -0.67
    vey
    -0.67
    POSITIVE LOGITS
     namely
    0.82
     homophobia
    0.69
     timely
    0.69
    Magikarp
    0.63
     disabling
    0.63
     disabilities
    0.62
     aesthetics
    0.61
     nuisance
    0.61
     including
    0.60
     fingerprints
    0.60
    Act Density 0.164%

    No Known Activations