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

    Neuronpedia

    INDEX
    Explanations

    specific verbs related to recounting information or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate evidence or reporting of information or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istries
    -0.96
    rontal
    -0.85
    ierce
    -0.78
    osterone
    -0.74
    enburg
    -0.71
    aukee
    -0.68
    vae
    -0.68
    incial
    -0.67
    ardo
    -0.67
    estern
    -0.66
    POSITIVE LOGITS
     evidenced
    0.76
     happens
    0.76
     by
    0.75
     unfolds
    0.73
     articulated
    0.71
     narrated
    0.71
     develops
    0.66
    ream
    0.66
     elaborated
    0.65
     AST
    0.65
    Act Density 0.048%

    No Known Activations