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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uala
    -0.39
     Flavoring
    -0.38
     Cosponsors
    -0.37
    aukee
    -0.37
    Reviewer
    -0.37
    APTER
    -0.35
    Reviewed
    -0.35
    edIn
    -0.35
    ¥µ
    -0.35
    byter
    -0.34
    POSITIVE LOGITS
    term
    0.41
    shore
    0.41
     term
    0.35
    itude
    0.35
     nutshell
    0.34
    sighted
    0.34
    est
    0.34
    itud
    0.33
     foreseeable
    0.33
    hern
    0.32
    Act Density 0.656%

    No Known Activations