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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and questions related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opoulos
    -0.21
    ÑĥÑħ
    -0.15
    775
    -0.15
    Probe
    -0.15
    åį
    -0.14
     Probe
    -0.14
    #echo
    -0.14
    fila
    -0.14
    æľĭ
    -0.14
     Sale
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥ«ãĥī
    0.16
    acey
    0.15
    338
    0.15
    isl
    0.15
    avit
    0.15
    cai
    0.15
    éĽª
    0.15
    agger
    0.14
    andler
    0.14
    VERRIDE
    0.14
    Act Density 0.031%

    No Known Activations