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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "connect"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fic
    -0.16
    icot
    -0.15
    uming
    -0.15
    NECT
    -0.15
    berman
    -0.14
    annis
    -0.14
     League
    -0.14
    istry
    -0.14
    arding
    -0.14
    úa
    -0.14
    POSITIVE LOGITS
    elman
    0.16
    YPE
    0.15
    krom
    0.14
    HEMA
    0.14
    onical
    0.13
    wel
    0.13
     Graham
    0.13
    oup
    0.13
    \:
    0.13
    spr
    0.13
    Act Density 0.020%

    No Known Activations