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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to causing an effect or prompting an action

    oai_token-act-pair · gpt-3.5-turbo

    words related to motivation or causes of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĦ
    -0.85
     Seym
    -0.80
    umbing
    -0.77
    anamo
    -0.73
    alg
    -0.71
    ereo
    -0.69
    alon
    -0.67
     Faces
    -0.67
    roma
    -0.66
    iere
    -0.65
    POSITIVE LOGITS
     wedge
    0.83
     away
    0.82
     driving
    0.77
     toward
    0.72
     towards
    0.71
     mobilization
    0.69
     driven
    0.68
     innovation
    0.67
     home
    0.66
    iday
    0.65
    Act Density 0.049%

    No Known Activations