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

    Neuronpedia

    INDEX
    Explanations

    phrases related to projects or plans

    oai_token-act-pair · gpt-3.5-turbo

    words related to visual elements and components in artistic or project contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.72
     prest
    -0.72
     territ
    -0.71
    emale
    -0.69
    avorite
    -0.68
     challeng
    -0.67
     behav
    -0.66
    farious
    -0.65
     destro
    -0.65
     Seym
    -0.62
    POSITIVE LOGITS
    ¶
    0.66
     ]
    0.63
    ="#
    0.63
    resses
    0.62
    cloud
    0.58
    =\"
    0.58
    coins
    0.57
    lement
    0.57
    ="
    0.57
    ":"
    0.56
    Act Density 0.211%

    No Known Activations