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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to various fields like technology, programming, medicine, and culinary arts

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating usage, preferences, and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥ³
    -0.74
    ForgeModLoader
    -0.68
    alos
    -0.63
    vernment
    -0.57
    ãĥĪ
    -0.54
    ãĥ«
    -0.52
    ãĥķãĤ¡
    -0.52
     slime
    -0.51
     ACTIONS
    -0.51
    ãĥīãĥ©
    -0.51
    POSITIVE LOGITS
    .
    1.07
    .;
    0.98
    .(
    0.96
    ;
    0.94
    .:
    0.88
    .[
    0.88
     alongside
    0.86
    .}
    0.85
    .</
    0.85
    .�
    0.84
    Act Density 0.412%

    No Known Activations