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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cke
    -0.19
    lod
    -0.17
    adb
    -0.16
    å²Ĺ
    -0.16
    contres
    -0.15
    (=)
    -0.15
    ceae
    -0.15
    slaught
    -0.15
    ovice
    -0.15
    rab
    -0.14
    POSITIVE LOGITS
    nt
    0.18
    've
    0.18
    ’ve
    0.15
     potential
    0.15
    ed
    0.15
    ़
    0.15
    anova
    0.15
     potentially
    0.14
    -have
    0.14
    ãĥ³ãĥĦ
    0.14
    Act Density 0.110%

    No Known Activations