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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military actions or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bet
    -0.85
     ancest
    -0.74
     preval
    -0.72
     elevation
    -0.69
     strugg
    -0.68
    igmatic
    -0.68
     partName
    -0.66
     scrut
    -0.63
     istg
    -0.62
    picture
    -0.61
    POSITIVE LOGITS
    ãĤ¦
    0.73
    tnc
    0.71
    ESSION
    0.70
    ãĥĺ
    0.70
    ARS
    0.67
    ãĥīãĥ©
    0.66
     civilians
    0.66
    ãĤ¯
    0.66
    ãĤ¸
    0.66
    Ö¼
    0.65
    Act Density 0.130%

    No Known Activations