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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating things that are in progress or being planned

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to projects or developments in progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gencies
    -0.65
     cared
    -0.63
    dad
    -0.62
    1978
    -0.62
     screamed
    -0.60
    CVE
    -0.60
    ãĥĺ
    -0.60
    Viol
    -0.59
     proclaimed
    -0.58
    gio
    -0.57
    POSITIVE LOGITS
     plans
    0.85
     phases
    0.81
     feasibility
    0.77
     phase
    0.75
     Phase
    0.74
    abouts
    0.74
    rils
    0.74
     stages
    0.69
     developments
    0.67
     revisions
    0.67
    Act Density 0.402%

    No Known Activations