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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and expressions of belief or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    memberof
    -0.15
    otti
    -0.15
    eza
    -0.14
    scri
    -0.14
     Serif
    -0.14
    ptest
    -0.14
    asil
    -0.14
    blr
    -0.14
    rella
    -0.14
    licable
    -0.14
    POSITIVE LOGITS
     initially
    0.23
     thought
    0.22
     might
    0.22
     originally
    0.20
     previously
    0.20
     feared
    0.20
     commonly
    0.19
     appearances
    0.19
    might
    0.18
     Initially
    0.17
    Act Density 0.066%

    No Known Activations